From: Mel Gorman Date: Wed, 27 Sep 2006 08:49:51 +0000 (-0700) Subject: [PATCH] Have x86 use add_active_range() and free_area_init_nodes X-Git-Tag: v2.6.19-rc1~981 X-Git-Url: http://pilppa.com/gitweb/?a=commitdiff_plain;h=4cfee88ad30acc47f02b8b7ba3db8556262dce1e;p=linux-2.6-omap-h63xx.git [PATCH] Have x86 use add_active_range() and free_area_init_nodes Size zones and holes in an architecture independent manner for x86. [akpm@osdl.org: build fix] Signed-off-by: Mel Gorman Cc: Dave Hansen Cc: Andy Whitcroft Cc: Andi Kleen Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "Keith Mannthey" Cc: "Luck, Tony" Cc: KAMEZAWA Hiroyuki Cc: Yasunori Goto Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig index 758044f5e71..3fd9f1e8b09 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -598,12 +598,10 @@ config ARCH_SELECT_MEMORY_MODEL def_bool y depends on ARCH_SPARSEMEM_ENABLE -source "mm/Kconfig" +config ARCH_POPULATES_NODE_MAP + def_bool y -config HAVE_ARCH_EARLY_PFN_TO_NID - bool - default y - depends on NUMA +source "mm/Kconfig" config HIGHPTE bool "Allocate 3rd-level pagetables from highmem" diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c index 76a524b4c90..814cdebf737 100644 --- a/arch/i386/kernel/setup.c +++ b/arch/i386/kernel/setup.c @@ -1089,22 +1089,20 @@ static unsigned long __init setup_memory(void) void __init zone_sizes_init(void) { - unsigned long zones_size[MAX_NR_ZONES] = { 0, }; - unsigned int max_dma, low; - - max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; - low = max_low_pfn; - - if (low < max_dma) - zones_size[ZONE_DMA] = low; - else { - zones_size[ZONE_DMA] = max_dma; - zones_size[ZONE_NORMAL] = low - max_dma; #ifdef CONFIG_HIGHMEM - zones_size[ZONE_HIGHMEM] = highend_pfn - low; + unsigned long max_zone_pfns[MAX_NR_ZONES] = { + virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT, + max_low_pfn, + highend_pfn}; + add_active_range(0, 0, highend_pfn); +#else + unsigned long max_zone_pfns[MAX_NR_ZONES] = { + virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT, + max_low_pfn}; + add_active_range(0, 0, max_low_pfn); #endif - } - free_area_init(zones_size); + + free_area_init_nodes(max_zone_pfns); } #else extern unsigned long __init setup_memory(void); diff --git a/arch/i386/kernel/srat.c b/arch/i386/kernel/srat.c index 83db411b3aa..32413122c4c 100644 --- a/arch/i386/kernel/srat.c +++ b/arch/i386/kernel/srat.c @@ -54,8 +54,6 @@ struct node_memory_chunk_s { static struct node_memory_chunk_s node_memory_chunk[MAXCHUNKS]; static int num_memory_chunks; /* total number of memory chunks */ -static int zholes_size_init; -static unsigned long zholes_size[MAX_NUMNODES * MAX_NR_ZONES]; extern void * boot_ioremap(unsigned long, unsigned long); @@ -135,47 +133,6 @@ static void __init parse_memory_affinity_structure (char *sratp) "enabled and removable" : "enabled" ) ); } -/* Take a chunk of pages from page frame cstart to cend and count the number - * of pages in each zone, returned via zones[]. - */ -static __init void chunk_to_zones(unsigned long cstart, unsigned long cend, - unsigned long *zones) -{ - unsigned long max_dma; - extern unsigned long max_low_pfn; - - int z; - unsigned long rend; - - /* FIXME: MAX_DMA_ADDRESS and max_low_pfn are trying to provide - * similarly scoped information and should be handled in a consistant - * manner. - */ - max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; - - /* Split the hole into the zones in which it falls. Repeatedly - * take the segment in which the remaining hole starts, round it - * to the end of that zone. - */ - memset(zones, 0, MAX_NR_ZONES * sizeof(long)); - while (cstart < cend) { - if (cstart < max_dma) { - z = ZONE_DMA; - rend = (cend < max_dma)? cend : max_dma; - - } else if (cstart < max_low_pfn) { - z = ZONE_NORMAL; - rend = (cend < max_low_pfn)? cend : max_low_pfn; - - } else { - z = ZONE_HIGHMEM; - rend = cend; - } - zones[z] += rend - cstart; - cstart = rend; - } -} - /* * The SRAT table always lists ascending addresses, so can always * assume that the first "start" address that you see is the real @@ -220,7 +177,6 @@ static int __init acpi20_parse_srat(struct acpi_table_srat *sratp) memset(pxm_bitmap, 0, sizeof(pxm_bitmap)); /* init proximity domain bitmap */ memset(node_memory_chunk, 0, sizeof(node_memory_chunk)); - memset(zholes_size, 0, sizeof(zholes_size)); num_memory_chunks = 0; while (p < end) { @@ -284,6 +240,7 @@ static int __init acpi20_parse_srat(struct acpi_table_srat *sratp) printk("chunk %d nid %d start_pfn %08lx end_pfn %08lx\n", j, chunk->nid, chunk->start_pfn, chunk->end_pfn); node_read_chunk(chunk->nid, chunk); + add_active_range(chunk->nid, chunk->start_pfn, chunk->end_pfn); } for_each_online_node(nid) { @@ -392,57 +349,7 @@ int __init get_memcfg_from_srat(void) return acpi20_parse_srat((struct acpi_table_srat *)header); } out_err: + remove_all_active_ranges(); printk("failed to get NUMA memory information from SRAT table\n"); return 0; } - -/* For each node run the memory list to determine whether there are - * any memory holes. For each hole determine which ZONE they fall - * into. - * - * NOTE#1: this requires knowledge of the zone boundries and so - * _cannot_ be performed before those are calculated in setup_memory. - * - * NOTE#2: we rely on the fact that the memory chunks are ordered by - * start pfn number during setup. - */ -static void __init get_zholes_init(void) -{ - int nid; - int c; - int first; - unsigned long end = 0; - - for_each_online_node(nid) { - first = 1; - for (c = 0; c < num_memory_chunks; c++){ - if (node_memory_chunk[c].nid == nid) { - if (first) { - end = node_memory_chunk[c].end_pfn; - first = 0; - - } else { - /* Record any gap between this chunk - * and the previous chunk on this node - * against the zones it spans. - */ - chunk_to_zones(end, - node_memory_chunk[c].start_pfn, - &zholes_size[nid * MAX_NR_ZONES]); - } - } - } - } -} - -unsigned long * __init get_zholes_size(int nid) -{ - if (!zholes_size_init) { - zholes_size_init++; - get_zholes_init(); - } - if (nid >= MAX_NUMNODES || !node_online(nid)) - printk("%s: nid = %d is invalid/offline. num_online_nodes = %d", - __FUNCTION__, nid, num_online_nodes()); - return &zholes_size[nid * MAX_NR_ZONES]; -} diff --git a/arch/i386/mm/discontig.c b/arch/i386/mm/discontig.c index 941d1a5ebab..51e3739dd22 100644 --- a/arch/i386/mm/discontig.c +++ b/arch/i386/mm/discontig.c @@ -157,21 +157,6 @@ static void __init find_max_pfn_node(int nid) BUG(); } -/* Find the owning node for a pfn. */ -int early_pfn_to_nid(unsigned long pfn) -{ - int nid; - - for_each_node(nid) { - if (node_end_pfn[nid] == 0) - break; - if (node_start_pfn[nid] <= pfn && node_end_pfn[nid] >= pfn) - return nid; - } - - return 0; -} - /* * Allocate memory for the pg_data_t for this node via a crude pre-bootmem * method. For node zero take this from the bottom of memory, for @@ -227,6 +212,8 @@ static unsigned long calculate_numa_remap_pages(void) unsigned long pfn; for_each_online_node(nid) { + unsigned old_end_pfn = node_end_pfn[nid]; + /* * The acpi/srat node info can show hot-add memroy zones * where memory could be added but not currently present. @@ -276,6 +263,7 @@ static unsigned long calculate_numa_remap_pages(void) node_end_pfn[nid] -= size; node_remap_start_pfn[nid] = node_end_pfn[nid]; + shrink_active_range(nid, old_end_pfn, node_end_pfn[nid]); } printk("Reserving total of %ld pages for numa KVA remap\n", reserve_pages); @@ -369,45 +357,22 @@ void __init numa_kva_reserve(void) void __init zone_sizes_init(void) { int nid; - - - for_each_online_node(nid) { - unsigned long zones_size[MAX_NR_ZONES] = {0, }; - unsigned long *zholes_size; - unsigned int max_dma; - - unsigned long low = max_low_pfn; - unsigned long start = node_start_pfn[nid]; - unsigned long high = node_end_pfn[nid]; - - max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; - - if (node_has_online_mem(nid)){ - if (start > low) { -#ifdef CONFIG_HIGHMEM - BUG_ON(start > high); - zones_size[ZONE_HIGHMEM] = high - start; -#endif - } else { - if (low < max_dma) - zones_size[ZONE_DMA] = low; - else { - BUG_ON(max_dma > low); - BUG_ON(low > high); - zones_size[ZONE_DMA] = max_dma; - zones_size[ZONE_NORMAL] = low - max_dma; -#ifdef CONFIG_HIGHMEM - zones_size[ZONE_HIGHMEM] = high - low; -#endif - } - } + unsigned long max_zone_pfns[MAX_NR_ZONES] = { + virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT, + max_low_pfn, + highend_pfn + }; + + /* If SRAT has not registered memory, register it now */ + if (find_max_pfn_with_active_regions() == 0) { + for_each_online_node(nid) { + if (node_has_online_mem(nid)) + add_active_range(nid, node_start_pfn[nid], + node_end_pfn[nid]); } - - zholes_size = get_zholes_size(nid); - - free_area_init_node(nid, NODE_DATA(nid), zones_size, start, - zholes_size); } + + free_area_init_nodes(max_zone_pfns); return; }